Persistent knowledge in CRHQ — how agents remember facts, preferences, and context across sessions.
Memory gives agents persistent knowledge that carries across sessions. Instead of starting fresh every conversation, agents can recall facts, preferences, decisions, and context you've established before.
When important information comes up in a conversation — your preferences, key decisions, project details, or technical facts — agents can store it as a memory. In future sessions, agents automatically search memory for relevant context.
Memories are categorized by type:
| Type | Purpose | Example |
|---|---|---|
| Fact | Objective information | "The production database is PostgreSQL 17 on port 5432" |
| Preference | How you like things done | "Always use TypeScript, never plain JavaScript" |
| Decision | Choices that were made | "We chose Stripe over PayPal for payment processing" |
| Context | Background information | "The client's target audience is enterprise SaaS buyers" |
Memories can be tagged for organization. Tags help both humans and agents find relevant information:
#project-name — Project-specific context#technical — Technical decisions and configurations#client — Client preferences and requirements#process — How things should be doneMemory supports two types of search:
Semantic search means an agent searching for "database setup" will also find memories about "PostgreSQL configuration" — even if those exact words weren't used.